无需状态估计的像素级敏捷飞行演示
Demonstrating Agile Flight from Pixels without State Estimation
AI总结：
该研究提出首个无需显式状态估计的视觉驱动四旋翼系统，通过非对称演员-评论家强化学习训练策略，结合Swin-transformer门检测器，实现了最高40km/h、2g加速度的敏捷飞行，可依托现成硬件运行。
摘要：
四旋翼飞行器是最敏捷的飞行机器人之一。尽管近年来基于学习的控制和计算机视觉领域取得了进展，但自主无人机仍依赖显式状态估计。另一方面，人类飞行员仅依靠无人机机载摄像头的第一视角视频流，就能将平台性能发挥到极限，并在未知环境中稳健飞行。据我们所知，我们提出了首个基于视觉的四旋翼系统，该系统能以高速自主穿越一系列门，同时直接将像素映射为控制指令。与专业无人机竞速飞行员一样，我们的系统不使用显式状态估计，且采用与人类相同的控制指令（总推力和机体角速度）。我们演示了速度最高达40公里/小时、加速度最高达2g的敏捷飞行。这一成果通过强化学习（RL）训练基于视觉的策略实现。训练借助可访问特权信息的非对称演员-评论家框架完成。为克服基于图像的强化学习训练过程中的计算复杂度问题，我们将门的内边缘用作传感器抽象。这种简单但稳健、与任务相关的表征可在训练期间进行模拟，无需渲染图像。部署阶段则使用基于Swin Transformer的门检测器。我们的方法可通过标准的现成硬件实现自主敏捷飞行。尽管我们的演示聚焦于无人机竞速，但我们认为该方法的影响不止于无人机竞速，可为未来结构化环境中的实际应用研究奠定基础。
英文摘要：
Quadrotors are among the most agile flying robots. Despite recent advances in learning-based control and computer vision, autonomous drones still rely on explicit state estimation. On the other hand, human pilots only rely on a first-person-view video stream from the drone onboard camera to push the platform to its limits and fly robustly in unseen environments. To the best of our knowledge, we present the first vision-based quadrotor system that autonomously navigates through a sequence of gates at high speeds while directly mapping pixels to control commands. Like professional drone-racing pilots, our system does not use explicit state estimation and leverages the same control commands humans use (collective thrust and body rates). We demonstrate agile flight at speeds up to 40km/h with accelerations up to 2g. This is achieved by training vision-based policies with reinforcement learning (RL). The training is facilitated using an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use the inner edges of the gates as a sensor abstraction. This simple yet robust, task-relevant representation can be simulated during training without rendering images. During deployment, a Swin-transformer-based gate detector is used. Our approach enables autonomous agile flight with standard, off-the-shelf hardware. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
